no code implementations • 11 Mar 2024 • Jean V. Alves, Diogo Leitão, Sérgio Jesus, Marco O. P. Sampaio, Javier Liébana, Pedro Saleiro, Mário A. T. Figueiredo, Pedro Bizarro
Learning to defer (L2D) aims to improve human-AI collaboration systems by learning how to defer decisions to humans when they are more likely to be correct than an ML classifier.
no code implementations • 16 Jan 2024 • Ricardo Moreira, Jacopo Bono, Mário Cardoso, Pedro Saleiro, Mário A. T. Figueiredo, Pedro Bizarro
Lastly, explanation methods should be efficient and not compromise the performance of the predictive task.
1 code implementation • 20 Dec 2023 • Jean V. Alves, Diogo Leitão, Sérgio Jesus, Marco O. P. Sampaio, Pedro Saleiro, Mário A. T. Figueiredo, Pedro Bizarro
Financial fraud detection is a high-stakes setting where algorithms and human experts often work in tandem; however, there are no publicly available datasets for L2D concerning this important application of human-AI teaming.
no code implementations • 29 Mar 2023 • José Pombal, Pedro Saleiro, Mário A. T. Figueiredo, Pedro Bizarro
Data valuation is a ML field that studies the value of training instances towards a given predictive task.
no code implementations • 14 Mar 2023 • Mário A. T. Figueiredo, Catarina A. Oliveira
We select as the most likely causal direction the one in which the conditional pmf is closer to a uniform channel (UC).
no code implementations • 4 Sep 2022 • Fábio Mendonça, Sheikh Shanawaz Mostafa, Fernando Morgado-Dias, Antonio G. Ravelo-García, Mário A. T. Figueiredo
ProBoost, a new boosting algorithm for probabilistic classifiers, is proposed in this work.
no code implementations • 13 Jul 2022 • José Pombal, André F. Cruz, João Bravo, Pedro Saleiro, Mário A. T. Figueiredo, Pedro Bizarro
The unparalleled ability of machine learning algorithms to learn patterns from data also enables them to incorporate biases embedded within.
no code implementations • 27 Jun 2022 • Diogo Leitão, Pedro Saleiro, Mário A. T. Figueiredo, Pedro Bizarro
Human-AI collaboration (HAIC) in decision-making aims to create synergistic teaming between human decision-makers and AI systems.
no code implementations • 27 Jun 2022 • José Pombal, Pedro Saleiro, Mário A. T. Figueiredo, Pedro Bizarro
The unparalleled ability of machine learning algorithms to learn patterns from data also enables them to incorporate biases embedded within.
1 code implementation • 4 Mar 2022 • Gonçalo R. A. Faria, André F. T. Martins, Mário A. T. Figueiredo
Recent work has shown promising results in causal discovery by leveraging interventional data with gradient-based methods, even when the intervened variables are unknown.
1 code implementation • 4 Aug 2021 • André F. T. Martins, Marcos Treviso, António Farinhas, Pedro M. Q. Aguiar, Mário A. T. Figueiredo, Mathieu Blondel, Vlad Niculae
In contrast, for finite domains, recent work on sparse alternatives to softmax (e. g., sparsemax, $\alpha$-entmax, and fusedmax), has led to distributions with varying support.
1 code implementation • 30 Nov 2020 • João Bento, Pedro Saleiro, André F. Cruz, Mário A. T. Figueiredo, Pedro Bizarro
Although recurrent neural networks (RNNs) are state-of-the-art in numerous sequential decision-making tasks, there has been little research on explaining their predictions.
1 code implementation • 3 Nov 2020 • João Pedro Araújo, Mário A. T. Figueiredo, Miguel Ayala Botto
The main difference between AQL and SPAQL is that the latter learns time-invariant policies, where the mapping from states to actions does not depend explicitly on the time step.
no code implementations • 1 Sep 2020 • Guilherme G. P. Freitas Pires, Mário A. T. Figueiredo
The present work overcomes this by using normalizing flows as components in a mixture model and devising an end-to-end training procedure for such a model.
1 code implementation • 15 Jun 2020 • Matilde Tristany Farinha, Sérgio Pequito, Pedro A. Santos, Mário A. T. Figueiredo
Artificial neural networks, one of the most successful approaches to supervised learning, were originally inspired by their biological counterparts.
2 code implementations • NeurIPS 2020 • André F. T. Martins, António Farinhas, Marcos Treviso, Vlad Niculae, Pedro M. Q. Aguiar, Mário A. T. Figueiredo
Exponential families are widely used in machine learning; they include many distributions in continuous and discrete domains (e. g., Gaussian, Dirichlet, Poisson, and categorical distributions via the softmax transformation).
Ranked #36 on Visual Question Answering (VQA) on VQA v2 test-std
no code implementations • ICLR Workshop DeepDiffEq 2019 • Marek Śmieja, Maciej Kołomycki, Łukasz Struski, Mateusz Juda, Mário A. T. Figueiredo
This paper introduces an approach to filling in missing data based on deep auto-encoder models, adequate to high-dimensional data exhibiting complex dependencies, such as images.
no code implementations • 18 Jan 2020 • Marek Śmieja, Łukasz Struski, Mário A. T. Figueiredo
In this paper, we introduce a neural network framework for semi-supervised clustering (SSC) with pairwise (must-link or cannot-link) constraints.
no code implementations • 27 Sep 2018 • Jorge Pessoa, Helena Aidos, Pedro Tomás, Mário A. T. Figueiredo
Deep learning (DL) is having a revolutionary impact in image processing, with DL-based approaches now holding the state of the art in many tasks, including image compression.
2 code implementations • 19 Jul 2018 • Miguel Monteiro, Mário A. T. Figueiredo, Arlindo L. Oliveira
In this paper, we test whether this algorithm, which was shown to improve semantic segmentation for 2D RGB images, is able to improve segmentation quality for 3D multi-modal medical images.
no code implementations • 2 Jan 2018 • Afonso M. Teodoro, José M. Bioucas-Dias, Mário A. T. Figueiredo
The recently proposed plug-and-play (PnP) framework allows leveraging recent developments in image denoising to tackle other, more involved, imaging inverse problems.
no code implementations • 6 Sep 2017 • Marina Ljubenović, Mário A. T. Figueiredo
Blind image deblurring (BID) is an ill-posed inverse problem, usually addressed by imposing prior knowledge on the (unknown) image and on the blurring filter.
no code implementations • 8 Feb 2017 • Afonso M. Teodoro, José M. Bioucas-Dias, Mário A. T. Figueiredo
Recent frameworks, such as the so-called plug-and-play, allow us to leverage the developments in image denoising to tackle other, and more involved, problems in image processing.
no code implementations • 23 May 2016 • Afonso M. Teodoro, José M. Bioucas-Dias, Mário A. T. Figueiredo
State-of-the-art algorithms for imaging inverse problems (namely deblurring and reconstruction) are typically iterative, involving a denoising operation as one of its steps.
no code implementations • 12 Feb 2016 • Afonso M. Teodoro, José M. Bioucas-Dias, Mário A. T. Figueiredo
This paper proposes using a Gaussian mixture model as a prior, for solving two image inverse problems, namely image deblurring and compressive imaging.
3 code implementations • 15 Sep 2014 • Xiangrong Zeng, Mário A. T. Figueiredo
The ordered weighted $\ell_1$ norm (OWL) was recently proposed, with two different motivations: its good statistical properties as a sparsity promoting regularizer; the fact that it generalizes the so-called {\it octagonal shrinkage and clustering algorithm for regression} (OSCAR), which has the ability to cluster/group regression variables that are highly correlated.
no code implementations • 11 Apr 2014 • Xiangrong Zeng, Mário A. T. Figueiredo
We consider a new family of regularizers, termed {\it weighted sorted $\ell_1$ norms} (WSL1), which generalizes the recently introduced {\it octagonal shrinkage and clustering algorithm for regression} (OSCAR) and also contains the $\ell_1$ and $\ell_{\infty}$ norms as particular instances.
1 code implementation • 28 Mar 2014 • Nuno Fachada, Mário A. T. Figueiredo, Vitor V. Lopes, Rui C. Martins, Agostinho C.Rosa
This paper proposes new clustering criteria for distinguishing Saccharomyces cerevisiae (yeast) strains using their spectrometric signature.
no code implementations • 20 Feb 2014 • Xiangrong Zeng, Mário A. T. Figueiredo
The subgradient of the 2D one-sided $\ell_1$ (or $\ell_2$) penalty and the projection onto the $K$-sparsity and TV or MTV constraint can be computed efficiently, allowing the appliaction of algorithms of the {\it forward-backward splitting} (a. k. a.
no code implementations • 20 Feb 2014 • Xiangrong Zeng, Mário A. T. Figueiredo
We propose a new method, {\it binary fused compressive sensing} (BFCS), to recover sparse piece-wise smooth signals from 1-bit compressive measurements.
no code implementations • 20 Feb 2014 • Xiangrong Zeng, Mário A. T. Figueiredo
We show that the proximity operator of 2OSCAR can be computed based on that of OSCAR.
no code implementations • 20 Feb 2014 • Xiangrong Zeng, Mário A. T. Figueiredo
We propose a new method, {\it robust binary fused compressive sensing} (RoBFCS), to recover sparse piece-wise smooth signals from 1-bit compressive measurements.
no code implementations • 18 Oct 2013 • Xiangrong Zeng, Mário A. T. Figueiredo
We propose a novel SPARsity and Clustering (SPARC) regularizer, which is a modified version of the previous octagonal shrinkage and clustering algorithm for regression (OSCAR), where, the proposed regularizer consists of a $K$-sparse constraint and a pair-wise $\ell_{\infty}$ norm restricted on the $K$ largest components in magnitude.
no code implementations • 24 Sep 2013 • Xiangrong Zeng, Mário A. T. Figueiredo
The OSCAR regularizer has a non-trivial proximity operator, which limits its applicability.